Provided is a self-correcting stock price movement predictor built with Artificial Intelligence (AI) techniques that are for empirical data and represent trends on a particular day for an identified stock. Robots, Internet bots, and so forth, are used to source events in real time in the World Wide Web and which may have a potential impact on the movement of the stock. When the web is spidered (or browsed), a device is able to capture the data, which might have an impact on the stock. The data may be structured and ranked using various techniques, including AI techniques. These techniques are applied in order to predict the stock behavior and the movement of that particular stock. An output of the tool is provided to automatically determine an action to take relative to an identified stock.
Legal claims defining the scope of protection, as filed with the USPTO.
1. A method, comprising: obtaining from at least a subset of a plurality of sources, by a system comprising a memory, a processor, and a machine learning module, a plurality of event information related to an event at substantially a same time as a reporting of the event, the reporting being captured in at least the subset of the plurality of sources; identifying, by the machine learning module, data determined to be relevant for an identified value indicator from the obtained event information; extracting, by the system, a set of data from the identified data at substantially the same time as the reporting of the event, wherein the extracting comprises preparing the extracted data to be incorporated into a database, and wherein the preparation comprises tagging the extracted data with a plurality of matrix tags; incorporating, by the system, the tagged extracted set of data into the database; mining, by the system, the database for other tagged extracted data that is similar to the set of data associated with the identified value indicator; determining, by the system, a result set based at least in part on processing by a predictive data analytics and an Intelligence Quota (IQ) engine of the mined tagged extracted data, wherein the predictive data analytics and the IQ engine employ the plurality of matrix tags and a pendulum ratio that controls a level of predictions to be calculated, and wherein the result set of the processing is determined at substantially the same time as the reporting of the event; and communicating, by the system, the result set to a device in or near real time.
2. The method of claim 1 , wherein at least one of the plurality of sources is restricted to a subset of the plurality of sources comprising strictly electronically connected data feeds.
3. The method of claim 2 , wherein the communicating the result set employs the at least one of the plurality of sources.
4. The method of claim 1 , wherein the identifying of data determined to be relevant for the identified value indicator from the obtained event information, comprises determinations based at least in part on a pre-determined machine learned confidence level for the obtained event information to be associated with the identified value indicator.
5. The method of claim 1 , wherein the identified value indicator is a registered stock value.
6. The method of claim 1 , wherein the plurality of matrix tags comprise a class score master, an event score, a weightage score and a confidence level.
7. The method of claim 1 , wherein the result set comprises at least two of a predicted price movement of the identified value indicator, a price-movement-associated confidence level, and a time window for which either of the predicted price movement and the confidence level or both are applicable.
8. The method of claim 1 , wherein the identifying data determined to be relevant, the tagging the extracted data with the plurality of matrix tags, and the mining the database for other tagged extracted data that is similar each employ artificial intelligence techniques that incorporate feedback loops.
9. A system, comprising: a processor; a machine learning module; and a memory that stores executable instructions that, when executed by the processor, facilitate performance of operations along with the machine learning module, comprising: obtaining from at least a subset of a plurality of sources, by the system, a plurality of event information related to an event at substantially a same time as a reporting of the event, the reporting being captured in at least the subset of the plurality of sources; identifying, by the machine learning module, data determined to be relevant for an identified value indicator from the obtained event information; extracting, by the system, a set of data from the identified data at substantially the same time as the reporting of the event, wherein the extracting comprises preparing the extracted data to be incorporated into a database, and wherein the preparation comprises tagging the extracted data with a plurality of matrix tags; incorporating, by the system, the tagged extracted set of data into the database; mining, by the system, the database for other tagged extracted data that is similar to the set of data associated with the identified value indicator; determining, by the system, a result set based at least in part on processing by a predictive data analytics and an Intelligence Quota (IQ) engine of the mined tagged extracted data, wherein the predictive data analytics and the IQ engine employ the plurality of matrix tags and a pendulum ratio that controls a level of predictions to be calculated, and wherein the result set of the processing is determined at substantially the same time as the reporting of the event; and communicating, by the system, the result set to a device in or near real time.
10. The system of claim 9 , wherein at least one of the plurality of sources is restricted to a subset of the plurality of sources comprising strictly electronically connected data feeds.
11. The system of claim 10 , wherein the communicating the result set employs the at least one of the plurality of sources.
12. The system of claim 9 , wherein the identifying of data determined to be relevant for the identified value indicator from the obtained event information, comprises determinations based at least in part on a pre-determined machine learned confidence level for the obtained event information to be associated with the identified value indicator.
13. The system of claim 9 , wherein the identified value indicator is a registered stock value.
14. The system of claim 9 , wherein the plurality of matrix tags comprise a class score master, an event score, a weightage score and a confidence level.
15. The system of claim 9 , wherein the result set comprises at least two of a predicted price movement of the identified value indicator, a price-movement-associated confidence level, and a time window for which either of the predicted price movement and the confidence level or both are applicable.
16. The system of claim 9 , wherein the identifying data determined to be relevant, the tagging the extracted data with the plurality of matrix tags, and the mining the database for other tagged extracted data that is similar each employ artificial intelligence techniques that incorporate feedback loops.
17. A non-transitory computer-readable storage device that stores executable instructions that, in response to execution, cause a system comprising a processor and a machine learning module to perform operations, comprising: obtaining from at least a subset of a plurality of sources, by the system, a plurality of event information related to an event at substantially a same time as a reporting of the event, the reporting being captured in at least the subset of the plurality of sources; identifying, by the machine learning module, data determined to be relevant for an identified value indicator from the obtained event information; extracting, by the system, a set of data from the identified data at substantially the same time as the reporting of the event, wherein the extracting comprises preparing the extracted data to be incorporated into a database, and wherein the preparation comprises tagging the extracted data with a plurality of matrix tags; incorporating, by the system, the tagged extracted set of data into the database; mining, by the system, the database for other tagged extracted data that is similar to the set of data associated with the identified value indicator; determining, by the system, a result set based at least in part on processing by a predictive data analytics and an Intelligence Quota (IQ) engine of the mined tagged extracted data, wherein the predictive data analytics and the IQ engine employ the plurality of matrix tags and a pendulum ratio that controls a level of predictions to be calculated, and wherein the result set of the processing is determined at substantially the same time as the reporting of the event; and communicating, by the system, the result set to a device in or near real time.
18. The non-transitory computer readable storage device of claim 17 , further: wherein the identifying of data determined to be relevant for the identified value indicator from the obtained event information, comprises determinations based at least in part on a pre-determined machine learned confidence level for the obtained event information to be associated with the identified value indicator; wherein the identified value indicator is a registered stock value; and wherein the plurality of matrix tags comprise a class score master, an event score, a weightage score and a confidence level; wherein the result set comprises at least two of a predicted price movement of the identified value indicator, a price-movement-associated confidence level, and a time window for which either of the predicted price movement and the confidence level or both are applicable; and wherein the identifying data determined to be relevant, the tagging the extracted data with the plurality of matrix tags, and the mining the database for other tagged extracted data that is similar each employ artificial intelligence techniques that incorporate feedback loops.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
May 5, 2017
March 30, 2021
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.